RF-DETR with multi-scale feature fusion and explainable attention for accurate brain tumor detection in MRI
Abstract
Magnetic Resonance Imaging (MRI) is very crucial in the diagnosis and examination of brain tumors because it can give good images of the soft tissues and anatomy. Nonetheless, the detection and localization of the tumor areas are still difficult due to differences in tumor shape, size, and pattern of intensity changes amongst scans of different MRIs. The proposed study is an improved transformer-based detection framework that can combine RF-DETR with multi-scale feature fusion and explainable attention mechanisms to detect brain tumors better. The proposed solution utilizes a hierarchical feature extraction model, which is based on a convolutional convolutional backbone and the multi-scale fusion to extract fine-grained and global contextual information. A transformer encoder-decoder network is used to end-to-end approximate long-range spatial dependencies and predict locations and class labels of tumors. Moreover, explainable attention module is added to indicate the areas that play the most important part in model predictions and, therefore, enhance interpretability and clinical importance. The presented model is tested on the brain MRI data which includes four classes: brain, glioma, meningioma, and pituitary. Experimental results show that it has high detection performance, with a precision of 0.9545, recall of 0.9494, F1-score of 0.9520, mAP at 0.5 of 0.9432 and mAP at 0.5:0.95 of 0.7403 on the validation set. Comparative analysis has revealed that the proposed framework is better in detecting accuracy, and moderate computational complexity and outperforms the current CNN-based and transformer-based models. The ablation research also confirms that multi-scale feature fusion, as well as explainable attention, are helpful in providing impressive performance on models. The findings show that the proposed framework can offer reliable, precise, and interpretable tumor detection and is thus a promising tool in the field of computer-assisted diagnosis and clinical decision support used in neuroimaging studies.
Related
- HAAF-RT-DETR: hybrid attention and high-resolution feature fusion based RT-DETR for kidney stone detection
- ASC-YOLOv8n: Enhanced multi-scale feature fusion for accurate detection of four cigar appearance defects
- HayabusaNet: Hybrid attention-based multiscale fusion CNN for accurate and efficient brain tumor classification in MRI scans
- Dual-stream attention and feature fusion for human activity recognition via wearable sensors
- Cross-corpus consensus feature selection for language-invariant Parkinson’s disease detection: a dual-stream acoustic and spectrogram-attention framework
BibTeX
@article{hashmi2026rfdetr,
title = {{RF-DETR with multi-scale feature fusion and explainable attention for accurate brain tumor detection in MRI}},
author = {Arshad Hashmi and Muzammil Hussain and Anas W. Abulfarj and Mohammed Ameen and Hasan J. Alyamani and Faisal Binzagr},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-73522-7},
url = {https://www.nature.com/articles/s41598-026-73522-7},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - RF-DETR with multi-scale feature fusion and explainable attention for accurate brain tumor detection in MRI
AU - Arshad Hashmi
AU - Muzammil Hussain
AU - Anas W. Abulfarj
AU - Mohammed Ameen
AU - Hasan J. Alyamani
AU - Faisal Binzagr
PY - 2026
DA - 2026/10/07
JO - Scientific Reports
DO - 10.1038/s41598-026-73522-7
UR - https://www.nature.com/articles/s41598-026-73522-7
AB - Magnetic Resonance Imaging (MRI) is very crucial in the diagnosis and examination of brain tumors because it can give good images of the soft tissues and anatomy. Nonetheless, the detection and localization of the tumor areas are still difficult due to differences in tumor shape, size, and pattern of intensity changes amongst scans of different MRIs. The proposed study is an improved transformer-based detection framework that can combine RF-DETR with multi-scale feature fusion and explainable attention mechanisms to detect brain tumors better. The proposed solution utilizes a hierarchical feature extraction model, which is based on a convolutional convolutional backbone and the multi-scale fusion to extract fine-grained and global contextual information. A transformer encoder-decoder network is used to end-to-end approximate long-range spatial dependencies and predict locations and class labels of tumors. Moreover, explainable attention module is added to indicate the areas that play the most important part in model predictions and, therefore, enhance interpretability and clinical importance. The presented model is tested on the brain MRI data which includes four classes: brain, glioma, meningioma, and pituitary. Experimental results show that it has high detection performance, with a precision of 0.9545, recall of 0.9494, F1-score of 0.9520, mAP at 0.5 of 0.9432 and mAP at 0.5:0.95 of 0.7403 on the validation set. Comparative analysis has revealed that the proposed framework is better in detecting accuracy, and moderate computational complexity and outperforms the current CNN-based and transformer-based models. The ablation research also confirms that multi-scale feature fusion, as well as explainable attention, are helpful in providing impressive performance on models. The findings show that the proposed framework can offer reliable, precise, and interpretable tumor detection and is thus a promising tool in the field of computer-assisted diagnosis and clinical decision support used in neuroimaging studies.
SN - 2045-2322
ER -